Hacker News new | ask | show | jobs
by nancyminusone 398 days ago
LLMs are great at tasks that involve written language. If your task does not involve written language, they suck. That's the main limitation. No matter how hard you push, AI is not a 'do everything machine' which is how it's being hyped.
2 comments
Flamentono2 396 days ago
Written language is very powerful apparently. After all LLM can generate SVG, python code to use Blender etc.

One demo i saw with LLM and code use: "Generate a small snake game" and because the author still had the Blender MCP tool connection, the LLM decided to generate 3D assets through Blender for that game.

link
ranie93 398 days ago
Can "everything" be mapped to a written language task (i.e. described)?
link